Tensorflow
- Introduction to Tensorflow
- Deep Learning and Neural Networks
- Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN)
Deep Learning and Neural Networks
Deep Learning Fundamentals
Branch of machine learning.
Deep Learning is a subset of machine learning that is based on artificial neural networks with representation learning. It can be supervised, semi-supervised, or unsupervised and can learn and represent almost any function given enough data and compute time.
Definition of Deep Learning
Deep Learning is a machine learning technique that teaches computers to do what comes naturally to humans: learn by example. It is a key technology behind driverless cars, enabling them to recognize a stop sign or to distinguish a pedestrian from a lamppost. It is the key to voice control in consumer devices like phones, tablets, TVs, and hands-free speakers.
Importance and Advantages of Deep Learning
Deep Learning is gaining much popularity due to its accuracy when trained with large amounts of data. The main advantage of Deep Learning networks is that they often continue to improve as the size of your data increases. In the traditional machine learning domain, you reach a plateau in performance after a certain amount of data.
Differences between Machine Learning and Deep Learning
While both fall under the broad category of artificial intelligence, deep learning is what powers the most human-like artificial intelligence. Here are some differences:
- Data Dependencies: Deep learning algorithms require more data than traditional machine learning algorithms. The performance of deep learning algorithms improves with an increase in the size of the data.
- Hardware Dependencies: Deep learning algorithms require a far more robust hardware setup than traditional machine learning algorithms. They often need a GPU (Graphical Processing Unit), which is why cloud-based platforms are often used for deep learning computation.
- Feature Engineering: In traditional machine learning, most of the applied features need to be identified by an expert and then hand-coded as per the domain and data type. Deep learning algorithms, on the other hand, try to learn high-level features from data in an incremental manner. This is a very distinctive part of Deep Learning and a major step ahead of traditional machine learning.
Real-World Applications of Deep Learning
Deep Learning is used in the most advanced fields of technology. Some of them are:
- Automated Driving: Automotive researchers are using deep learning to automatically detect objects such as stop signs and traffic lights. In addition, deep learning is used to detect pedestrians, which helps decrease accidents.
- Aerospace and Defense: Deep learning is used for object recognition and identification from satellites that locate areas of interest, and identify objects to improve map accuracy.
- Medical Research: Cancer researchers are using deep learning to automatically detect cancer cells. Teams at UCLA built an advanced microscope that yields a high-dimensional data set used to train a deep learning application to accurately identify cancer cells.
Overview of Deep Learning Frameworks
There are several frameworks that allow for the design, training, and validation of deep learning models. Some of the most popular ones include TensorFlow, Keras, PyTorch, and Caffe. These frameworks provide the tools and libraries to easily design and deploy deep learning models.
In conclusion, Deep Learning is a rapidly growing field and is proving to be a valuable asset in our society. It is a technology that is helping to make our lives easier, safer, and more efficient.